Adam Gleave

Can you elaborate a bit more what you had in mind? If we just naively moved the current example code into say the `examples/` directory we'd get the benefit of...

Extracting things from first cell of notebook sounds doable but tricky, would probably require a Sphinx extension. But I think it's easy to just embed files as code snippets in...

Thanks for the report. Always adding `normalize_input_layer` does seem like busted behavior, may not make sense for a variety of reward networks and input types. I'd suggest modifying the config...

> One could also change the default [here](https://github.com/HumanCompatibleAI/imitation/blob/40a2a559706e50bf60d7cc388a2c36dd0d4e8619/src/imitation/util/networks.py#L213), though that wouldn't be visible in the sacred config if we remove the hook. Maybe non-trivial defaults like this should always be...

> I wanted to ask couple of related questions. > > 1. I noticed that the `hash(item.nodeid)` doesn't give a good distribution on my workloads. I.e. if I have 8...

I'm fine with MIT license but this is largely the work of @atucker so he should make the final decision on this. We should also add a `README.md`...

So long as the environments implement the standard Gym interface it should work fine with this code. In the notebook, all you need to do is replace `gym.make(env_name)` with whatever...

> Thanks for the infos, I'll give it a try in the next few days. Meanwhile I opened the notebook locally with Jupyter but when it executes the line importing...

That seems likely. TensorFlow is normally compiled to use extensions like AVX2 that may be missing in VirtualBox. There's a long thread at at https://github.com/tensorflow/tensorflow/issues/17411 You could try compiling TensorFlow...

You should be able to run most of the code without MuJoCo, you can just change `gym[mujoco]` to `gym`. Most the environments in the paper require MuJoCo though so you...